Open freaad opened 7 years ago
Can you check the version of TensorFlow you are using? Typing tensorflow.__version__
It looks very similar to errors with pre-1.0 TF versions.
mine is 0.12
Me too encounter some error in this notebook I run this
from datasets import pascalvoc_2007
from datasets import pascalvoc_2012
DATASET_DIR = '/media/paul/DataExt4/PascalVOC/dataset/'
SPLIT_NAME = 'test'
BATCH_SIZE = 16
# Dataset provider loading data from the dataset.
dataset = pascalvoc_2007.get_split(SPLIT_NAME, DATASET_DIR)
provider = slim.dataset_data_provider.DatasetDataProvider(dataset,
shuffle=False,
num_epochs=1,
common_queue_capacity=2 * BATCH_SIZE,
common_queue_min=BATCH_SIZE)
[image, shape, bboxes, labels] = provider.get(['image', 'shape', 'object/bbox', 'object/label'])
print('Dataset:', dataset.data_sources, '|', dataset.num_samples)
and there the output
NotFoundError Traceback (most recent call last)
<ipython-input-16-4ead4da6636f> in <module>()
12 num_epochs=1,
13 common_queue_capacity=2 * BATCH_SIZE,
---> 14 common_queue_min=BATCH_SIZE)
15 [image, shape, bboxes, labels] = provider.get(['image', 'shape', 'object/bbox', 'object/label'])
16 print('Dataset:', dataset.data_sources, '|', dataset.num_samples)
/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/slim/python/slim/data/dataset_data_provider.py in __init__(self, dataset, num_readers, reader_kwargs, shuffle, num_epochs, common_queue_capacity, common_queue_min, record_key, seed)
89 capacity=common_queue_capacity,
90 min_after_dequeue=common_queue_min,
---> 91 seed=seed)
92
93 items = dataset.decoder.list_items()
/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/slim/python/slim/data/parallel_reader.py in parallel_read(data_sources, reader_class, num_epochs, num_readers, reader_kwargs, shuffle, dtypes, capacity, min_after_dequeue, seed, scope)
208 key, value: a tuple of keys and values from the data_source.
209 """
--> 210 data_files = get_data_files(data_sources)
211 with ops.name_scope(scope, 'parallel_read'):
212 filename_queue = tf_input.string_input_producer(
/usr/local/lib/python3.5/dist-packages/tensorflow/contrib/slim/python/slim/data/parallel_reader.py in get_data_files(data_sources)
277 else:
278 if '*' in data_sources or '?' in data_sources or '[' in data_sources:
--> 279 data_files = gfile.Glob(data_sources)
280 else:
281 data_files = [data_sources]
/usr/local/lib/python3.5/dist-packages/tensorflow/python/lib/io/file_io.py in get_matching_files(filename)
280 return [compat.as_str_any(matching_filename)
281 for matching_filename in pywrap_tensorflow.GetMatchingFiles(
--> 282 compat.as_bytes(filename), status)]
283
284
/usr/lib/python3.5/contextlib.py in __exit__(self, type, value, traceback)
64 if type is None:
65 try:
---> 66 next(self.gen)
67 except StopIteration:
68 return
/usr/local/lib/python3.5/dist-packages/tensorflow/python/framework/errors_impl.py in raise_exception_on_not_ok_status()
464 None, None,
465 compat.as_text(pywrap_tensorflow.TF_Message(status)),
--> 466 pywrap_tensorflow.TF_GetCode(status))
467 finally:
468 pywrap_tensorflow.TF_DeleteStatus(status)
NotFoundError: /media/paul/DataExt4/PascalVOC/dataset
change biases_initializer=tf.zeros_initializer()
into biases_initializer=tf.zeros_initializer
works for me.
I am running the ipynb on the windows. I have tensor flow anaconda version. I face the error in the 6 box. I don't get it about this error. Also I want to run my personel image. Any tool can you recommend to make like pascal voc. I've already collect the image. I just need to make annotation.
TypeError Traceback (most recent call last)